GitHub (@github) header
GitHub (@github) profile picture

GitHub

@github

The AI-powered developer platform to build, scale, and deliver secure software.

 San Francisco, CA
github.com
Joined February 2008
  • Tweets11.1K
  • Following335
  • Followers2.7M
3.2KMedia
Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)
Frontier performance at a fraction of the cost. In the @ArtificialAnlys Coding Agent Index, Copilot Fusion Max scored within two points of Claude Code with Opus 5.5 Max at about half the API cost per task. Get 30% off through Nov. 30. Try it now. ⬇️ docs.github.com/copilot/conc…
Chart titled "Coding Agent Index vs. Cost per Task" by Artificial Analysis. The chart displays Artificial Analysis Coding Agent Index vs. average pay-per-token API cost per task (USD). It compares various agents, including some from Claude Code, Codex, Antigravity CLI, DeepSeek Harness, Grok Build, Opencode, Muse Code, Kimi Code CLI, and GitHub Copilot. The x-axis represents higher cost per task (USD) to lower cost per task (USD), and the y-axis represents the coding agent index. The chart highlights a "Most Attractive Quadrant" in green and uses dots to differentiate agents. Copilot Fusion (max) sits within the most attractive quadrant.

ALT Chart titled "Coding Agent Index vs. Cost per Task" by Artificial Analysis. The chart displays Artificial Analysis Coding Agent Index vs. average pay-per-token API cost per task (USD). It compares various agents, including some from Claude Code, Codex, Antigravity CLI, DeepSeek Harness, Grok Build, Opencode, Muse Code, Kimi Code CLI, and GitHub Copilot. The x-axis represents higher cost per task (USD) to lower cost per task (USD), and the y-axis represents the coding agent index. The chart highlights a "Most Attractive Quadrant" in green and uses dots to differentiate agents. Copilot Fusion (max) sits within the most attractive quadrant.

Bar chart titled "Artificial Analysis Coding Agent Index". Incorporates 3 benchmarks: FrontierCode v1.1, Terminal-Bench 4.0, SWE-Atlas-QnA-AA. A higher scroe denotes higher average intelligence across becnhmarks. Copilot Fusion Max from GitHub Copilot has a score of 60. The chart also includes various coding agents from Claude Code, Devin Fusion CLI, Antigravity CLI, Codex, Grok Build, DeepSeek Harness, Muse Code, Opencode, Antigravity CLI, and Kimi Code CLI, with scores ranging from 62 to 41. Source and logo of Artificial Analysis are included at the bottom.

ALT Bar chart titled "Artificial Analysis Coding Agent Index". Incorporates 3 benchmarks: FrontierCode v1.1, Terminal-Bench 4.0, SWE-Atlas-QnA-AA. A higher scroe denotes higher average intelligence across becnhmarks. Copilot Fusion Max from GitHub Copilot has a score of 60. The chart also includes various coding agents from Claude Code, Devin Fusion CLI, Antigravity CLI, Codex, Grok Build, DeepSeek Harness, Muse Code, Opencode, Antigravity CLI, and Kimi Code CLI, with scores ranging from 62 to 41. Source and logo of Artificial Analysis are included at the bottom.

131
72
89
651
124,269
Solve problems, accelerate development, and keep developers responsible for the results. Three Java Champions share how they use GitHub Copilot 👇 github.blog/ai-and-ml/github…
How 3 Java Champions are using GitHub Copilot for increased productivity

How 3 Java Champions are using GitHub Copilot for increased productivity

Three Java Champions share how they use GitHub Copilot to solve problems, accelerate development, and keep humans responsible for the results.

github.blog
19
7
3
38
22,537
🆕 @GoogleAI's Gemini 4 Carbon is now generally available in GitHub Copilot. Designed for complex coding, agentic, and reasoning tasks, it has a special focus in security work. Try it in the GitHub Copilot app, CLI, and @code. github.blog/changelog/2026-1…
Gemini 4 Carbon in GitHub Copilot - GitHub Changelog

Gemini 4 Carbon in GitHub Copilot - GitHub Changelog

Gemini 4 Carbon, Google’s latest model, is now generally available in GitHub Copilot. It is designed for complex coding, agentic, and reasoning tasks, with a focus on secure code generation…

github.blog
60
32
22
296
44,882
It's here ➡️ @AnthropicAI's Claude Fable 5.2 is now generally available in GitHub Copilot. Our early testing shows Fable 5.2: • solved more tasks than Fable 5.1 while using fewer steps and tool calls • completed difficult tasks that earlier models missed Try Fable 5.2 for complex, multistep coding jobs across large codebases. Find it in the GitHub Copilot app, CLI, or @code. github.blog/changelog/2026-1…
Claude Fable 5.2 in GitHub Copilot - GitHub Changelog

Claude Fable 5.2 in GitHub Copilot - GitHub Changelog

Claude Fable 5.2, Anthropic’s newest Fable model, is now generally available in GitHub Copilot. You can use it for complex, multistep coding tasks across large codebases. In early testing, Fable…

github.blog
70
50
21
465
66,879
Claude Fable 5.2 requires data retention by default to operate Anthropic's safety classifiers. Zero data retention access is available for certain eligible enterprise customers. support.claude.com/articles/…
Data retention practices for Covered Models | Claude Help Center

Data retention practices for Covered Models | Claude Help Center

support.claude.com
5
2
5
17
11,141
Both Slack and Teams surfaces are GA and on a weekly release cadence. Keep your team in flow 🏎️ github.blog/changelog/2026-1…
Image from Mario Rodriguez (@mariorod1)
6
13
21
52
19,455
Your agent may have started the work, but you can finish the task in your IDE. Open a GitHub Copilot app session directly in @code. The task, plan, conversation, and code changes all come too (so you don't need to start over 😅). Here's every step ⬇️ github.blog/ai-and-ml/github…
How to continue a GitHub Copilot app session in VS Code

How to continue a GitHub Copilot app session in VS Code

Learn how to move an agent session from the GitHub Copilot app into VS Code without losing the conversation, code changes, or working context.

github.blog
65
28
15
207
46,425
How many donuts were eaten at #GitHubUniverse? 👀 Guess before the answer is revealed ⏳🍩
25
30
5
405
78,279
If you're into 3D printing, GitHub Copilot could help you out. ✨ @cassidoo shares the prompt she used to customize this GitHub-y microphone stand 🎤
32
17
5
191
47,642
💡 Bring all your related work together with projects in the GitHub Copilot app. Give Copilot a goal and it will coordinate the work. Your project can span one or more repos or focus on tasks that don't require one. Copilot can start sessions, set up recurring automations, or create artifacts; they'll show up in your project. 🗂️ Keep your sessions together to work toward one objective. Get started 👇 docs.github.com/copilot/how-…
81
42
24
472
90,741
Through internal testing, GitHub’s new Git storage architecture supported 5,000 concurrent agents working on a repo, sending 7,200 pushes per second, all while serving read traffic with consistently low latency.
Inside GitHub’s new Git storage architecture

Inside GitHub’s new Git storage architecture

Article · @github
117
119
74
1,152
105,500
What's the best way to learn? Give yourself permission to play, but time-box it. In our latest episode of the GitHub Podcast, @martinwoodward discusses how AI is changing open source, developer skills, and the joy of building things. Find it wherever you listen to podcasts or 👉 the-github-podcast.simplecas…
32
12
4
84
28,357
Here's a new way to assess your Copilot skills 💡 GitHub Copilot Verified Proficiency measures your demonstrated capability continuously as you do your work with Copilot. No exam, just data 📊 Learn more about calculating your proficiency level ⬇️ learn.github.com/proficienci…
Assess your skills with GitHub Copilot Verified Proficiency. Get evidence-based suggestions about how effectively you work with GitHub Copilot.

ALT Assess your skills with GitHub Copilot Verified Proficiency. Get evidence-based suggestions about how effectively you work with GitHub Copilot.

53
35
14
304
50,564
GitHub retweeted
David Poll (@depoll) profile picture
David Poll
@depollNov 5
Confession: I’ve scrolled past dozens of comments on a PR just to find out why I couldn’t merge it. More times than I’d like to admit. Agents have made this a lot worse. They push commits and leave review comments of their own, and all of it lands in the timeline. PR timelines have gotten dramatically noisier, and the few things you actually need to know get buried. My team is rethinking the foundations of the PR experience around that problem, and today the first piece went into public preview. The new Overview page puts merge readiness and your next step right at the top. A summary catches you up on review activity, and you can filter the conversation down to unresolved threads. It’s opt-in and rolling out through the weekend. This is a much-needed start, and there’s a lot more coming as we modernize PRs for the way software gets built now. If you try it, we’d love to hear what still sends you back to the classic view. github.blog/changelog/2026-1…
51
38
12
499
80,644
How we can secure 50% of the world's software. Traditionally, formal methods have been mostly used for safety-critical systems like operating systems, hypervisors, and databases. We're extending this to formally and empirically verify code correctness and security for full-stack web apps, one of the most common types of applications*, using the Proof-Driven Development Kit (PDD Kit). Coding agents now write code faster than anyone can review effectively. PDD Kit turns what the developer meant into a Verus specification. It then proves the AI-generated code meets that spec for every input. Researchers @alexlavaee, @MatthaiP39719, @Mappletons, and @k_cieslak break down Proof-Driven Development x Chopin in the blog here: githubnext.com/projects/pdd-… *44.4% of respondents work as full-stack (27.3%), back-end (13.5%), or front-end (3.6%) developers. Stack Overflow Developer Survey 2026, n = 25,767.
PDD Kit

PDD Kit

Building trust in the code that your agents wrote

githubnext.com
10
47
5
316
29,233
Instead of picking the model for each and every task, let Copilot Fusion route and orchestrate which model to use. ✅ Copilot Fusion balances performance and cost efficiency, picking from three execution patterns for the job: Single, Cascade, or Critique. All you need to do is choose the effort level. Try it in the GitHub Copilot app, Copilot CLI, and @code, now 30% off through November 30.
Diagram titled "Three execution patterns in Copilot Fusion," comparing three workflows: Single, where a primary model uses tools to request an answer; Cascade, where a primary model makes a first pass before a judge model either accepts its result as the answer or escalates to a repair model for a fresh-start answer; and Critique, where a primary model drafts an answer and a read-only critic either approves it as-is or requests a revision by the primary model.

ALT Diagram titled "Three execution patterns in Copilot Fusion," comparing three workflows: Single, where a primary model uses tools to request an answer; Cascade, where a primary model makes a first pass before a judge model either accepts its result as the answer or escalates to a repair model for a fresh-start answer; and Critique, where a primary model drafts an answer and a read-only critic either approves it as-is or requests a revision by the primary model.

58
38
14
359
52,258
Learn more about Copilot Fusion 💡 docs.github.com/copilot/conc…
About GitHub Copilot Fusion - GitHub Docs

About GitHub Copilot Fusion - GitHub Docs

Automatically select the right models and execution pattern for each task.

docs.github.com
1
1
14
9,744
Makerspace + Hack the Badge = two of my favourite activities at #GitHubUniverse! 🚀 Couldn't stop hacking when I got home. Now I can control the Octolamp from my conference badge over my home network. The fun doesn't end when the conference is over!
Virtual badger controlling virtual octolamp

ALT Virtual badger controlling virtual octolamp

2
4
21
10,085
Built my first mechanical keyboard! Some mistakes were made but I got it all working eventually! 😂
Image from Charlie Gerard (@devdevcharlie)
24
4
133
18,957
LGTM 👍
1
7
2,326
Built my first mechanical keyboard! Some mistakes were made but I got it all working eventually! 😂
Image from Charlie Gerard (@devdevcharlie)
24
4
133
18,957
Only at #GitHubUniverse does @martinwoodward get an entire stage to bring plushies to life with machine learning models 🐿️
35
38
6
363
79,529
Load more